Highlights d Trained a neural network to predict APA using data from over 3 million reporters d Visualized learned features to reveal a rich cis-regulatory code for APA d Developed and tested an algorithm to accurately engineer polyadenylation signals d Predicted and experimentally characterized over 12,000 human APA variants
SUMMARY Engineering gene and protein sequences with defined functional properties is a major goal of synthetic biology. Deep neural network models, together with gradient ascent-style optimization, show promise for sequence design. The generated sequences can however get stuck in local minima and often have low diversity. Here, we develop deep exploration networks (DENs), a class of activation-maximizing generative models, which minimize the cost of a neural network fitness predictor by gradient descent. By penalizing any two generated patterns on the basis of a similarity metric, DENs explicitly maximize sequence diversity. To avoid drifting into low-confidence regions of the predictor, we incorporate variational autoencoders to maintain the likelihood ratio of generated sequences. Using DENs, we engineered polyadenylation signals with more than 10-fold higher selection odds than the best gradient ascent-generated patterns, identified splice regulatory sequences predicted to result in highly differential splicing between cell lines, and improved on state-of-the-art results for protein design tasks.
Background Optimization of DNA and protein sequences based on Machine Learning models is becoming a powerful tool for molecular design. Activation maximization offers a simple design strategy for differentiable models: one-hot coded sequences are first approximated by a continuous representation, which is then iteratively optimized with respect to the predictor oracle by gradient ascent. While elegant, the current version of the method suffers from vanishing gradients and may cause predictor pathologies leading to poor convergence. Results Here, we introduce Fast SeqProp, an improved activation maximization method that combines straight-through approximation with normalization across the parameters of the input sequence distribution. Fast SeqProp overcomes bottlenecks in earlier methods arising from input parameters becoming skewed during optimization. Compared to prior methods, Fast SeqProp results in up to 100-fold faster convergence while also finding improved fitness optima for many applications. We demonstrate Fast SeqProp’s capabilities by designing DNA and protein sequences for six deep learning predictors, including a protein structure predictor. Conclusions Fast SeqProp offers a reliable and efficient method for general-purpose sequence optimization through a differentiable fitness predictor. As demonstrated on a variety of deep learning models, the method is widely applicable, and can incorporate various regularization techniques to maintain confidence in the sequence designs. As a design tool, Fast SeqProp may aid in the development of novel molecules, drug therapies and vaccines.
Background 3′-end processing by cleavage and polyadenylation is an important and finely tuned regulatory process during mRNA maturation. Numerous genetic variants are known to cause or contribute to human disorders by disrupting the cis-regulatory code of polyadenylation signals. Yet, due to the complexity of this code, variant interpretation remains challenging. Results We introduce a residual neural network model, APARENT2, that can infer 3′-cleavage and polyadenylation from DNA sequence more accurately than any previous model. This model generalizes to the case of alternative polyadenylation (APA) for a variable number of polyadenylation signals. We demonstrate APARENT2’s performance on several variant datasets, including functional reporter data and human 3′ aQTLs from GTEx. We apply neural network interpretation methods to gain insights into disrupted or protective higher-order features of polyadenylation. We fine-tune APARENT2 on human tissue-resolved transcriptomic data to elucidate tissue-specific variant effects. By combining APARENT2 with models of mRNA stability, we extend aQTL effect size predictions to the entire 3′ untranslated region. Finally, we perform in silico saturation mutagenesis of all human polyadenylation signals and compare the predicted effects of $${>}43$$ > 43 million variants against gnomAD. While loss-of-function variants were generally selected against, we also find specific clinical conditions linked to gain-of-function mutations. For example, we detect an association between gain-of-function mutations in the 3′-end and autism spectrum disorder. To experimentally validate APARENT2’s predictions, we assayed clinically relevant variants in multiple cell lines, including microglia-derived cells. Conclusions A sequence-to-function model based on deep residual learning enables accurate functional interpretation of genetic variants in polyadenylation signals and, when coupled with large human variation databases, elucidates the link between functional 3′-end mutations and human health.
Alternative polyadenylation (APA) is a major driver of transcriptome diversity in human 10 cells. Here, we use deep learning to predict APA from DNA sequence alone. We trained 11 our model (APARENT, APA REgression NeT) on isoform expression data from over three 12 million APA reporters, built by inserting random sequence into twelve distinct 3'UTR 13 contexts. Predictions are highly accurate across both synthetic and genomic contexts; 14 when tasked with inferring APA in human 3'UTRs, APARENT outperforms models trained 15 exclusively on endogenous data. Visualizing features learned across all network layers 16 reveals that APARENT recognizes sequence motifs known to recruit APA regulators, 17 discovers previously unknown sequence determinants of cleavage site selection, and 18integrates these features into a comprehensive, interpretable cis-regulatory code. Finally, 19we use APARENT to quantify the impact of genetic variants on APA. Our approach 20 detects pathogenic variants in a wide range of disease contexts, expanding our 21
Engineering gene sequences with defined functional properties is a major goal of synthetic biology. Deep neural network models, together with gradient ascent-style optimization, show promise for sequence generation. The generated sequences can however get stuck in local minima, have low diversity and their fitness depends heavily on initialization. Here, we develop deep exploration networks (DENs), a type of generative model tailor-made for searching a sequence space to minimize the cost of a neural network fitness predictor. By making the network compete with itself to control sequence diversity during training, we obtain generators capable of sampling hundreds of thousands of high-fitness sequences. We demonstrate the power of DENs in the context of engineering RNA isoforms, including polyadenylation and cell type-specific differential splicing. Using DENs, we engineered polyadenylation signals with more than 10-fold higher selection odds than the best gradient ascent-generated patterns and identified splice regulatory elements predicted to result in highly differential splicing between cell lines.
Most mammalian genes have multiple polyA sites, representing a substantial source of transcript diversity that is governed by the cleavage and polyadenylation (CPA) regulatory machinery. To better understand how these proteins govern polyA site choice we introduce CPA-Perturb-seq, a multiplexed perturbation screen dataset of 42 known CPA regulators with a 3' scRNA-seq readout that enables transcriptome-wide inference of polyA site usage. We develop a statistical framework to specifically identify perturbation-dependent changes in intronic and tandem polyadenylation, and discover modules of co-regulated polyA sites exhibiting distinct functional properties. By training a multi-task deep neural network (APARENT-Perturb) on our dataset, we delineate a cis-regulatory code that predicts responsiveness to perturbation and reveals interactions between distinct regulatory complexes. Finally, we leverage our framework to re-analyze published scRNA-seq datasets, identifying new regulators that affect the relative abundance of alternatively polyadenylated transcripts, and characterizing extensive cellular heterogeneity in 3' UTR length amongst antibody-producing cells. Our work highlights the potential for multiplexed single-cell perturbation screens to further our understanding of post-transcriptional regulation in vitro and in vivo.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.